RDMA/rxe: Add page invalidation support

On page invalidation, an MMU notifier callback is invoked to unmap DMA
addresses and update the driver page table(umem_odp->dma_list). The
callback is registered when an ODP-enabled MR is created.

Link: https://patch.msgid.link/r/20241220100936.2193541-3-matsuda-daisuke@fujitsu.com
Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

diff --git a/drivers/infiniband/sw/rxe/Makefile b/drivers/infiniband/sw/rxe/Makefile
index 5395a581f4bb245a55b45166333bdbc468be1bfa..93134f1d1d0ce4529d58b4937e2dcfe591f1ee16 100644 (file)
--- a/drivers/infiniband/sw/rxe/Makefile
+++ b/drivers/infiniband/sw/rxe/Makefile
@@ -23,3 +23,5 @@ rdma_rxe-y := \
        rxe_task.o \
        rxe_net.o \
        rxe_hw_counters.o
+
+rdma_rxe-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += rxe_odp.o

diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 738d3bca8d4f10486e7ced7dda98ee80085c02cc..465ab188c109c770ee6aada7ae578faad24bb2e2 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -181,4 +181,7 @@ static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp)
        return rxe_wr_opcode_info[opcode].mask[qp->ibqp.qp_type];
 }
 
+/* rxe_odp.c */
+extern const struct mmu_interval_notifier_ops rxe_mn_ops;
+
 #endif /* RXE_LOC_H */

diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c b/drivers/infiniband/sw/rxe/rxe_odp.c
new file mode 100644 (file)
index 0000000..2be8066
--- /dev/null
+++ b/drivers/infiniband/sw/rxe/rxe_odp.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2022-2023 Fujitsu Ltd. All rights reserved.
+ */
+
+#include <linux/hmm.h>
+
+#include <rdma/ib_umem_odp.h>
+
+#include "rxe.h"
+
+static bool rxe_ib_invalidate_range(struct mmu_interval_notifier *mni,
+                                   const struct mmu_notifier_range *range,
+                                   unsigned long cur_seq)
+{
+       struct ib_umem_odp *umem_odp =
+               container_of(mni, struct ib_umem_odp, notifier);
+       unsigned long start, end;
+
+       if (!mmu_notifier_range_blockable(range))
+               return false;
+
+       mutex_lock(&umem_odp->umem_mutex);
+       mmu_interval_set_seq(mni, cur_seq);
+
+       start = max_t(u64, ib_umem_start(umem_odp), range->start);
+       end = min_t(u64, ib_umem_end(umem_odp), range->end);
+
+       /* update umem_odp->dma_list */
+       ib_umem_odp_unmap_dma_pages(umem_odp, start, end);
+
+       mutex_unlock(&umem_odp->umem_mutex);
+       return true;
+}
+
+const struct mmu_interval_notifier_ops rxe_mn_ops = {
+       .invalidate = rxe_ib_invalidate_range,
+};